© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219006
    Prev
    Next
    INDEX
    Explanations

    responsibility of

    np_acts-logits-general · gemini-2.5-flash-lite

    influence after "its"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sorun
    0.48
     Proble
    0.47
     ²
    0.46
     problemas
    0.45
     problemler
    0.44
     a
    0.43
     escrever
    0.43
     područ
    0.43
     Resultados
    0.43
     Problems
    0.43
    POSITIVE LOGITS
    นี้
    0.52
    ลีก
    0.49
    มน
    0.47
    มะ
    0.47
    หว
    0.46
     ห
    0.46
    ôle
    0.46
    與
    0.45
    也
    0.45
    ส่ง
    0.45
    Activations Density 0.000%

    No Known Activations